Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
greenlit_checkA

Grade a deployed web app (built with Lovable, Bolt, v0, Replit, Emergent or by hand) A to F for what a stranger can use against it: secret keys shipped in its JavaScript (Stripe, OpenAI, OpenRouter, Supabase secret keys and 28 more kinds), a Supabase service_role key in the browser, source maps, clickjacking and missing security headers, plus launch basics (developer-only addresses, Stripe test mode, a test email sender, no https redirect, open CORS, missing DMARC on a custom domain). Every finding has a plain-English reason and a fix prompt; allFixes has every fix in one prompt, worst first. Reads only what the site serves to every visitor. Call it again after a fix: change shows what got fixed. For the user's own app, have them run npx greenlitlab <url> --mine: it also checks which database tables and storage buckets anyone can read, open sign-up, and public .env or .git files.

greenlit_scanA

Read a project folder on this computer for launch mistakes that can't be seen from outside, before deploying: Row Level Security policies whose condition is just true, tables created without RLS, Supabase edge functions with verify_jwt = false, Stripe webhook handlers that never verify the signature, secrets behind a public prefix (VITE_, NEXT_PUBLIC_), a tracked .env file, and an agent config with a writable database connection. Pattern-based, not a full code review. Reads names in .env files, never values. Each finding has a fix prompt.

greenlit_advisorA

Turn Supabase's Security or Performance Advisor results into plain-English findings with a fix prompt for each, worst first. Get the results from the Supabase MCP server's get_advisors tool (type "security") for the user's project, then pass them here as lints. This is the reliable way to learn which rules are too loose and whether strangers can change or delete data, which no outside check can see.

greenlit_questionsA

Seven launch questions only the app's owner can answer (backups and restore, separate test database, hard spending limits, payment webhook checks, outage alerts, email sender, database plan). Call with no arguments to get the questions and options to ask the user. Call with answers ({questionId: optionKey}) to get, for each gap, the fact that makes it matter and a fix prompt. Answers are the owner's word, never graded.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct input source and scope: local project files (greenlit_scan), Supabase advisor lints passed in (greenlit_advisor), owner-only answers (greenlit_questions), and a live deployed URL (greenlit_check). The descriptions explicitly delimit boundaries, e.g. scan covers what 'can't be seen from outside' while check covers 'what the site serves to every visitor', so an agent can pick correctly.

Naming Consistency4/5

All four names share a uniform greenlit_ prefix with a single short lowercase suffix, giving a predictable pattern. Minor deviation: suffixes mix verbs (scan, check) and nouns (advisor, questions), so it isn't a strict verb_noun convention, but it remains consistent and readable.

Tool Count4/5

Four tools for a focused launch-readiness audit product is well-scoped, with no redundant entries. It sits at the lean end of the 3-15 range, but each tool earns its place and none could be merged without losing a distinct input channel.

Completeness4/5

The surface covers the main launch-check layers: local code, external deployed site, database advisor lints, and owner-attested operational questions, each returning findings with fix prompts. Minor gaps exist, such as no consolidated report tool that aggregates findings across all four checks or persists results between runs beyond the per-run change diff.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues